It's all relative: Regression analysis with compositional predictors.

It's all relative: Regression analysis with compositional predictors.
复制标题

DOI:
10.1111/biom.13703
复制
发表时间:
2023-06
期刊:
影响因子:
1.9
通讯作者:
Chen, Kun
Chen, Kun
中科院分区:
数学3区
文献类型:
--
作者:
Li, Gen;Li, Yan;Chen, Kun

文献摘要

参考文献

相似文献

组成数据驻留在单形中,并测量部分与整体的分数或比例。大多数现有的回归方法,这样的数据依赖于对数比转换是不充分或不适当的建模高维数据与过多的零和层次结构。此外,由于组成部分之间的相互关系,这种模型通常缺乏直接的解释。我们开发了一个新的相对偏移回归框架,直接使用比例作为预测因子。新的框架提供了一个范式转变与成分预测回归分析,并提供了一个上级解释如何转移部分之间的浓度影响的反应。新的等稀疏和树引导的正则化方法和一个有效的平滑邻近梯度算法,以促进回归的特征聚集和降维。一个统一的有限样本预测误差界导出建议的正则化估计。我们在广泛的模拟研究和真实的肠道微生物组研究中证明了所提出的方法的有效性。在微生物组数据分类的指导下,该框架确定了与早产儿神经发育相关的不同分类水平的重要分类群。
Compositional data reside in a simplex and measure fractions or proportions of parts to a whole. Most existing regression methods for such data rely on log-ratio transformations that are inadequate or inappropriate in modeling high-dimensional data with excessive zeros and hierarchical structures. Moreover, such models usually lack a straightforward interpretation due to the interrelation between parts of a composition. We develop a novel relative-shift regression framework that directly uses proportions as predictors. The new framework provides a paradigm shift for regression analysis with compositional predictors and offers a superior interpretation of how shifting concentration between parts affects the response. New equi-sparsity and tree-guided regularization methods and an efficient smoothing proximal gradient algorithm are developed to facilitate feature aggregation and dimension reduction in regression. A unified finite-sample prediction error bound is derived for the proposed regularized estimators. We demonstrate the efficacy of the proposed methods in extensive simulation studies and a real gut microbiome study. Guided by the taxonomy of the microbiome data, the framework identifies important taxa at different taxonomic levels associated with the neurodevelopment of preterm infants.
与功能组成预测指标的对比对比回归:将早产儿的肠道微生物组轨迹与神经行为结果联系起来。
DOI: 10.1214/20-aoas1357
发表时间: 2020-09
期刊: The annals of applied statistics
影响因子: --
作者:
Sun Z;Xu W;Cong X;Li G;Chen K
通讯作者: Chen K
回归中的结构化子组合选择及其在微生物组数据分析中的应用
DOI: 10.1214/16-aoas1017
发表时间: 2017-06-01
影响因子: 1.8
作者:
Wang, Tao;Zhao, Hongyu
通讯作者: Zhao, Hongyu
DOI: 10.7554/elife.21887
发表时间: 2017-02-15
期刊: ELIFE
影响因子: 7.7
作者:
Silverman, Justin D.;Washburne, Alex D.;David, Lawrence A.
通讯作者: David, Lawrence A.
DOI: 10.1097/nnr.0000000000000208
发表时间: 2017
期刊: Nursing research
影响因子: 2.5
作者:
Cong X;Judge M;Xu W;Diallo A;Janton S;Brownell EA;Maas K;Graf J
通讯作者: Graf J
DOI: 10.1214/17-aoas1102
发表时间: 2018-03
期刊: The annals of applied statistics
影响因子: --
作者:
Randolph TW;Zhao S;Copeland W;Hullar M;Shojaie A
通讯作者: Shojaie A